Benchwarmers MCP server
io.github.WendellResearch-AI/benchwarmers·v0.5.5·1 starsAsk a collection of LLMs at once through your Benchwarmers server; verdicts pick the next panel.
not scanned yet
1 stars556 downloads/wk
Reviews
Write oneNobody has reviewed Benchwarmers yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Benchwarmers tools
No tool declarations could be read from the package source. They show once the server is installed.
How Benchwarmers compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 82/100
- higher than 63% of 48,255 servers
- GitHub stars
- 1
- more than 65% of 28,688 servers
- Downloads a week
- 556
- more than 89% of 12,191 servers with a package
Release history: 6 versions in the registry since 2026-10-23, latest 2026-11-02, typically one every 2 days.
Install Benchwarmers in Claude Code, Cursor or VS Code
Runs npx -y @wendellresearch-ai/benchwarmers on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add benchwarmers -- npx -y @wendellresearch-ai/benchwarmers
What the publisher says
From the Benchwarmers repository's README, as published. We do not edit it. Read it on GitHub
Put me in, coach.Every model on your bench gets its minutes.
Benchwarmers is a self-hosted panel gateway for LLMs. Your app asks for one of your collections, and the whole panel answers: the models you picked for that kind of work, plus explorer seats that rotate in the models you have used least. Every answer comes back side by side, labelled by model and seat. You check them against the real work and record a verdict, and those verdicts decide who sits on the next panel.
What it is best at:
answers. Where they disagree is where to look.
- Asking several models at once. One OpenAI-compatible request, a panel of
catch different things, and two models agreeing is not proof.
- Reviewing. Code review, claims about code, designs: different models
(reviewers, designers, enumerators), each with the models that do it best.
- Playing to each model's strengths. A collection per kind of work
the bench, so new and free models get tried beside the ones you trust, without you choosing them by hand.
- Giving every model playing time. Explorers cycle through the rest of
repositories, plus your verdicts on real work, instead of public leaderboards.
- Benchmarking on your own projects. A review suite seeded from your own
answering (retired automatically), and who is resting after a rate limit.
- Knowing who to bench. Who is confidently wrong, who has stopped
and one endpoint for every app, over any OpenAI-compatible provider or hub.
- Keeping free and cheap models useful. Health probes, learned rate limits
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Benchwarmers: common questions
- Is Benchwarmers MCP server safe?
- Mostly: it is graded B (82/100). Read the Benchwarmers safety report
- How do I install Benchwarmers?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Benchwarmers need an API key?
- Yes. The registry entry asks for
BENCHWARMERS_KEY. - Is Benchwarmers maintained?
- The last commit was 12 days ago (2026-10-23). The latest release is v0.5.5.
- How does Benchwarmers compare with other MCP servers?
- safety score 82/100 (higher than 63% of 48,255 servers); github stars 1 (more than 65% of 28,688 servers); downloads a week 556 (more than 89% of 12,191 servers with a package). Full comparison.